Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to different levels or degrees of something

    oai_token-act-pair · gpt-3.5-turbo

    mentions of levels or degrees of various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.80
    fect
    -0.73
     Andromeda
    -0.68
    ãĥĹ
    -0.67
     Twins
    -0.67
    sov
    -0.66
    vous
    -0.66
    ãĥĩ
    -0.66
    orius
    -0.65
     Rounds
    -0.65
    POSITIVE LOGITS
     crossings
    0.90
     assurance
    0.78
     levels
    0.76
    level
    0.74
     level
    0.73
     rise
    0.71
    xual
    0.69
     attainment
    0.68
     elevation
    0.68
     difference
    0.68
    Act Density 0.037%

    No Known Activations